{"ID":2862742,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.26166","arxiv_id":"2509.26166","title":"Beyond Overall Accuracy: Pose- and Occlusion-driven Fairness Analysis in Pedestrian Detection for Autonomous Driving","abstract":"Pedestrian detection plays a critical role in autonomous driving (AD), where ensuring safety and reliability is important. While many detection models aim to reduce miss-rates and handle challenges such as occlusion and long-range recognition, fairness remains an underexplored yet equally important concern. In this work, we systematically investigate how variations in the pedestrian pose -- including leg status, elbow status, and body orientation -- as well as individual joint occlusions, affect detection performance. We evaluate five pedestrian-specific detectors (F2DNet, MGAN, ALFNet, CSP, and Cascade R-CNN) alongside three general-purpose models (YOLOv12 variants) on the EuroCity Persons Dense Pose (ECP-DP) dataset. Fairness is quantified using the Equal Opportunity Difference (EOD) metric across various confidence thresholds. To assess statistical significance and robustness, we apply the Z-test. Our findings highlight biases against pedestrians with parallel legs, straight elbows, and lateral views. Occlusion of lower body joints has a more negative impact on the detection rate compared to the upper body and head. Cascade R-CNN achieves the lowest overall miss-rate and exhibits the smallest bias across all attributes. To the best of our knowledge, this is the first comprehensive pose- and occlusion-aware fairness evaluation in pedestrian detection for AD.","short_abstract":"Pedestrian detection plays a critical role in autonomous driving (AD), where ensuring safety and reliability is important. While many detection models aim to reduce miss-rates and handle challenges such as occlusion and long-range recognition, fairness remains an underexplored yet equally important concern. In this wor...","url_abs":"https://arxiv.org/abs/2509.26166","url_pdf":"https://arxiv.org/pdf/2509.26166v1","authors":"[\"Mohammad Khoshkdahan\",\"Arman Akbari\",\"Arash Akbari\",\"Xuan Zhang\"]","published":"2025-09-30T12:21:01Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Generative Adversarial Network\",\"Convolutional Neural Network\"]","has_code":false}